AI & ML

yulianuzhnenko Skill

Runs DiffDock generative diffusion models for blind protein-ligand docking against AlphaFold structures and ranks candidates by confidence scores.

aaroncharrier Bundle

Mentor-first quest design for data engineering and Codex or ChatGPT practice inside a real project. Use when Codex needs to create a new project quest, continuation quest, lightweight drill, debugging challenge, workflow practice quest, or prompt-engineering or context-engineering exercise with checkpoints, acceptance criteria, quest-wiki tracking, and a clear next step.

aaroncharrier Bundle

Resolve ambiguity in prompt-generation and other requests through a JSON-backed requirements interview stored in `.interview-engine/session-<yyyy-MM-dd_HH-mm-ss>/interview_questions.JSON`.

aaroncharrier Bundle

Generate Codex prompt artifacts only, including prompt files, templates, and reusable instruction sets, using an interview-first workflow. Use only when the user explicitly wants a prompt to be written, not when they want a direct answer, tutorial, guide, or general explanation.

aaroncharrier Bundle

Build downstream prompt file from interview output at `.interview-engine/session-<yyyy-MM-dd_HH-mm-ss>/interview_output.json`. Use when turning interview results into prompts. Never build a prompt from an unresolved interview or the raw user request alone.

shali10 Skill

Use when searching or extracting multimedia content including Bilibili/YouTube video subtitles, RSS feeds, and clean web text.

shali10 Skill

Use when designing or managing AI Agent persistent memory architectures to prevent context overflow while preserving durable facts.

shali10 Bundle

Use when designing, architecting, or benchmarking multi-tier autonomous AI Agent systems with layered memory, semantic caching, model routing, and deterministic guardrails.

whitebit-exchange Bundle

Supervised trading agent for WhiteBit. Runs one observe -> analyze -> decide -> guardrail -> act -> review cycle by composing the portfolio, market-data, technical-analysis, smart-money, order-execution, and trade-review skills. Sizes orders to a user-set risk policy and executes only after explicit per-order human approval. Use when the user says "run the agent", "trade for me", "manage this position", "run a cycle", or "wb-agent".

whitebit-exchange Skill

Reads account balances, open orders, positions, and trade history from WhiteBit MCP. Use before any trade decision or when reporting current account state. Use when the user says "my balance", "what do I have", "show my portfolio", "open orders", "my positions", "P&L", "trade history", or "how much USDT do I have".

whitebit-exchange Skill

Executes OCO (one-cancels-other) orders and agent-orchestrated TWAP strategies on WhiteBit. Use when managing complex entry/exit logic or splitting large orders to reduce market impact. Use when the user says "OCO", "one-cancels-other", "TWAP", "split my order", "reduce market impact", "take-profit and stop-loss together", or "execute over time".

whitebit-exchange Skill

Verifies that the WhiteBit MCP server is reachable and all tool categories respond correctly. Runs automatically before any trading skill if tools are unavailable. Use when the user says "is WhiteBit MCP running", "check connection", "ping WhiteBit", "are tools available", or when any WhiteBit MCP tool call fails unexpectedly.

whitebit-exchange Skill

Fetches live prices, order books, candles, and 24h stats from the WhiteBit MCP server. Use before any trade decision or when the user needs current market state. Use when the user says "price of", "what's BTC at", "show the chart", "order book for", "how much is", "24h stats", "available markets", or "what pairs does WhiteBit have".

whitebit-exchange Skill

Places, modifies, and cancels spot and collateral orders on WhiteBit via MCP tools. Use when executing a buy or sell decision on behalf of the user. Use when the user says "buy", "sell", "place an order", "cancel order", "modify order", "close position", "open a trade", or "execute".

avyayalaya Bundle

Use when designing pricing strategy, packaging tiers, monetization models, or evaluating pricing changes — pricing model selection, willingness-to-pay analysis, competitive pricing maps, package architecture, freemium conversion, usage-based pricing design, or price change impact assessment.

damon-stewart-1 Bundle

This skill should be used when the user says "/clear-prep", "prep for context clear", "prepare to clear", "handover prompt", "I'm going to clear the context", "relay context to a new instance", "snapshot my session", "session is getting full", "give me a handover", or "context is running out". Generates a self-contained handover prompt the user pastes into a cleared Claude Code instance so work continues seamlessly with zero re-explanation.

damon-stewart-1 Bundle

Rewrites a natural-language prompt into a structured, high-quality prompt that follows Anthropic's prompting best practices: explicit role, XML-tagged inputs, clear output format, examples, chain-of-thought scaffolding when warranted, and concrete success criteria. Use when the user says 'improve this prompt,' 'make this prompt better,' 'rewrite this prompt,' 'design a better prompt,' 'tune this prompt,' 'output a better prompt,' 'design your own prompt,' 'prompt for me,' or invokes /prompt-improver. Also use when the user pastes a draft prompt and asks for feedback or a stronger version.

frenzymath Bundle

Verify candidate proofs with the local proof verification MCP service. Use only when a full candidate proof of the entire problem has been assembled in markdown, and before publishing the final verified blueprint.

frenzymath Bundle

Synthesize the common stuck points across failed decomposition plans and recursive sub-agent reports. Use when the current batch of decomposition plans has failed.

rdleclerc Bundle

Use when material coding or agentic-system work runs as a goal/objective; needs a substantial plan, ledger, multi-agent orchestration, confidence gate, or completion orchestration; or asks which Uber subskill to use. Binds plan authority and routes proof to UberAccept.

rdleclerc Bundle

Use when an agent writes, removes, refactors, reviews, selects, or debugs tests, or decides which tests or product validation to run or whether they are needed. Do not use for command-only execution of an already specified test when no testing decision remains. Choose the smallest contract-preserving proof: one owner per contract, table-driven variants, current-checkout or installed-artifact evidence, and a named reason before escalating to broader suites.

rdleclerc Bundle

Do not auto-trigger from task similarity. Use only when explicitly named by the user or routed by ubergoal. Captures a lightweight, human-reviewed learning loop for skills, prompts, workflows, multi-agent coding protocols, or agentic-system playbooks after substantial or surprising runs.

cobibean Bundle

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

cobibean Bundle

Use this skill when starting or finishing substantial project work that would benefit from durable continuity across Codex, Claude, or other agent sessions. It teaches agents to read recent project memory before work and write concise Markdown session memory after meaningful work under docs/memory/YYYY-MM-DD/descriptive-slug-memory-YYYY-MM-DD.md, including what happened, what was learned, decisions made, gotchas, changed files, verification, constraints, open decisions, and useful next context while avoiding secrets and sensitive details.

cobibean Bundle

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

cobibean Bundle

Example-only skill that demonstrates how Shared Skills Registry MCP lists, previews, retrieves, and locally installs a small bundle.

cobibean Skill

Use when an agent or orchestrator needs to discover, inspect, retrieve, or install reusable skills from its configured Shared Skills Registry (SSR), while distinguishing registry access from caller-local installation.

songyw2003 Bundle

Inspect this workstation and configure, repair, or reproduce a Python project environment with a conda-first backend (falling back to uv when conda is unavailable or explicitly required), a project-named environment, reusable package caches, parallel package fetching, GPU-aware PyTorch selection, and a runnable smoke test. Use when Codex is asked to configure dependencies, create an environment, continue environment setup, reproduce a repository, install GPU packages, resolve CUDA or nvcc issues, or run a project demo after setup on this machine.

songyw2003 Bundle

Turn LLM-sounding content into plain, human, low-reading-age copy that a smart teenager could follow, in the spirit of how Richard Feynman explained hard ideas with simple words. Use when text reads as AI-generated, hard to follow, padded, or full of meta-commentary, or when the user wants a draft audited for AI-slop patterns without a rewrite. Goes beyond surface AI-tells: it strips notes-to-the- reader and meta-headings, forces every sentence into clear subject-verb-object, defines or deletes undefined jargon, audits each claim for truth and internal consistency, cuts length hard, and cuts named AI-slop patterns (banned words, colon reveals, fake-profound kickers, weasel attribution) while preserving the writer's real voice. Pairs with the humanizer skill (which handles AI vocabulary and style tells); run this for comprehension, substance, trust, and voice.

get-convex Skill

Add an AI agent / chatbot / RAG backend on Convex with @convex-dev/agent (durable threads, messages, tools, vector search). TRIGGER when the user wants an AI assistant/chatbot/agent or 'chat with my docs' feature. Calls models through the Convex AI Gateway — no provider key to manage.

blendsdk Bundle

Creates and maintains VitePress-compatible technical architecture documentation and architecture decision records (ADRs). Use when the user says "make_techdocs", "review_techdocs", "techdocs", "document the architecture", "create architecture docs", "write ADRs", or "architecture decision records". Covers two modes: make_techdocs to create or comprehensively regenerate the docs/ set (system overview, data model, API design, infrastructure, security, ADRs, developer guides, reference), and review_techdocs to run a 7-dimension health check (staleness, completeness, accuracy, ADR coverage, link health, diagram accuracy, getting-started) and produce a diagnostic report. Also fires automatically as an incremental or comprehensive update when an exec_plan phase or plan completes, or when make_requirements completes — but only if the project has opted in. Scope is technical/architectural docs for developers, NOT product/end-user documentation.

blendsdk Bundle

Sets up the CodeOps nested codeops/ layout in the current git repo — scaffolds a fresh skeleton or auto-migrates an existing flat-layout repo (requirements/ + plans/) into it. Use when the user says "setup_codeops", "/setup_codeops", "set up codeops", "initialize codeops", "migrate to the nested layout", "convert my plans/requirements to codeops/", or "scaffold the codeops structure". Detects repo state and dispatches: a marker (codeops/.codeops.yml) already present → no-op status report; a flat layout → migration (deterministic preview via scripts/codeops-migrate.sh, one confirmation, then git mv); neither → minimal fresh scaffold. Supports --dry-run (preview only) and --yes (apply without the prompt). Migration is git-mv-only, refuses a dirty tree, rejects path-traversal slugs, and is idempotent. setup_codeops is the SOLE writer of the layout marker.

blendsdk Bundle

Configures per-project model and effort routing so Opus + high/xhigh thinking is spent only where it changes output quality and high-volume mechanical work runs on Sonnet. Use when the user says "setup_routing", "/setup_routing", "set up model routing", "configure model routing", "route tasks by model", or "make this project use Opus/Sonnet per task". Independently analyzes the repo, classifies it into a sensitivity profile (Opus-dominant, Mixed core/scaffold, Sonnet-default, or a Balanced fallback), proposes a tag-driven routing policy, waits for explicit confirmation, then writes a sentinel-delimited routing block into the project CLAUDE.md. The pinned-model executor subagents the policy references ship with the plugin (agents/); customized per-project copies in .claude/agents/ are an opt-in override.

carthworks Skill

Prevents hardcoded secrets, API keys, passwords, and credentials in source code. Use this skill whenever the agent is writing code that connects to external services, reads config, handles authentication, or when a user asks about environment variables, .env files, or API keys. Also activates on "how do I store my API key", "is this safe to commit", or when the agent spots a string that looks like a credential.

carthworks Skill

Enforces high-quality git commit messages following Conventional Commits. Use this skill whenever the agent is about to run `git commit`, write a commit message, or help a user stage and commit changes. Blocks vague messages like "fix", "update", "changes", "wip". Also activates when the user asks "how should I write this commit?" or "help me commit this".

carthworks Skill

Enforces TypeScript strict mode configuration and type-safe coding patterns. Use when setting up a TypeScript project, reviewing tsconfig.json, fixing type errors, or when the user asks about TypeScript strictness, type safety, avoiding `any`, or improving their types. Also activates when the agent sees excessive use of `any`, type assertions (`as`), or non-null assertions (`!`).